Semantic Segmentation of Breast Ultrasound Image with Pyramid Fuzzy Uncertainty Reduction and Direction Connectedness Feature

Deep learning approaches have achieved impressive results in breast ultrasound (BUS) image segmentation. However, these methods did not solve uncertainty and noise in BUS images well. Meanwhile, they did not involve the context information of BUS images, either. To address this issue, we present a novel deep learning structure for BUS image semantic segmentation by analyzing the uncertainty using a pyramid fuzzy block and generating a novel feature based on connectedness. There are three major contributions in this paper: (1) the structure of pyramid fuzzy block; (2) a novel membership function based on multi-convolution layers; and (3) a novel context feature based on connectedness. The proposed methods are applied to two datasets: a BUS image benchmark with two categories (background and tumor) and a five-category BUS image dataset with fat layer, mammary layer, muscle layer, background, and tumor. The proposed method achieves the best results on both datasets compared with eight state-of-the-art deep learning-based approaches.

[1]  R. Chang,et al.  Tumor detection in automated breast ultrasound images using quantitative tissue clustering. , 2014, Medical physics.

[2]  Yuxuan Wang,et al.  Completely automated segmentation approach for breast ultrasound images using multiple-domain features. , 2012, Ultrasound in medicine & biology.

[3]  Bo Du,et al.  Boundary-Weighted Domain Adaptive Neural Network for Prostate MR Image Segmentation , 2019, IEEE Transactions on Medical Imaging.

[4]  J C Kent,et al.  Anatomy of the lactating human breast redefined with ultrasound imaging , 2005, Journal of anatomy.

[5]  Loïc Le Folgoc,et al.  Attention U-Net: Learning Where to Look for the Pancreas , 2018, ArXiv.

[6]  Min Xian,et al.  Fully automatic segmentation of breast ultrasound images based on breast characteristics in space and frequency domains , 2015, Pattern Recognit..

[7]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[10]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[11]  Xianglong Tang,et al.  An Effective Approach of Lesion Segmentation Within the Breast Ultrasound Image Based on the Cellular Automata Principle , 2012, Journal of Digital Imaging.

[12]  Lubomir M. Hadjiiski,et al.  Urinary bladder segmentation in CT urography using deep-learning convolutional neural network and level sets. , 2016, Medical physics.

[13]  Steven C. H. Hoi,et al.  Salient Object Detection With Pyramid Attention and Salient Edges , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Binjie Qin,et al.  Ultrasound Imaging Technologies for Breast Cancer Detection and Management: A Review. , 2018, Ultrasound in medicine & biology.

[15]  Ahmedin Jemal,et al.  Breast cancer statistics, 2019 , 2019, CA: a cancer journal for clinicians.

[16]  Chi-Wing Fu,et al.  Direction-Aware Spatial Context Features for Shadow Detection , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[17]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[18]  Supun Samarasekera,et al.  Fuzzy Connectedness and Object Definition: Theory, Algorithms, and Applications in Image Segmentation , 1996, CVGIP Graph. Model. Image Process..

[19]  Yingtao Zhang,et al.  Fuzzy Semantic Segmentation of Breast Ultrasound Image with Breast Anatomy Constraints , 2019, ArXiv.

[20]  Jayaram K. Udupa,et al.  Joint graph cut and relative fuzzy connectedness image segmentation algorithm , 2013, Medical Image Anal..

[21]  Xuelong Li,et al.  Automatic segmentation of breast lesions for interaction in ultrasonic computer-aided diagnosis , 2015, Inf. Sci..

[22]  George Papandreou,et al.  Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation , 2018, ECCV.

[23]  Youyong Kong,et al.  A Hierarchical Fused Fuzzy Deep Neural Network for Data Classification , 2017, IEEE Transactions on Fuzzy Systems.

[24]  Xianglong Tang,et al.  Probability density difference-based active contour for ultrasound image segmentation , 2010, Pattern Recognit..

[25]  Klaus-Robert Müller,et al.  Efficient BackProp , 2012, Neural Networks: Tricks of the Trade.

[26]  Heng-Da Cheng,et al.  Medical Knowledge Constrained Semantic Breast Ultrasound Image Segmentation , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[27]  Xiaogang Wang,et al.  Pyramid Scene Parsing Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Fakhri Karray,et al.  Fuzzy entropy: a brief survey , 2001, 10th IEEE International Conference on Fuzzy Systems. (Cat. No.01CH37297).

[29]  Joseph Bullock,et al.  XNet: a convolutional neural network (CNN) implementation for medical x-ray image segmentation suitable for small datasets , 2018, Medical Imaging.

[30]  Min Xian,et al.  A Fully Automatic Breast Ultrasound Image Segmentation Approach Based on Neutro-Connectedness , 2014, 2014 22nd International Conference on Pattern Recognition.

[31]  Reyer Zwiggelaar,et al.  Automated Breast Ultrasound Lesions Detection Using Convolutional Neural Networks , 2018, IEEE Journal of Biomedical and Health Informatics.

[32]  Fei Xu,et al.  A saliency model for automated tumor detection in breast ultrasound images , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[33]  Ying Wang,et al.  A Benchmark for Breast Ultrasound Image Segmentation (BUSIS) , 2018, ArXiv.